---
license: apache-2.0
base_model: facebook/wav2vec2-base
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: test-model
  results: []
---

<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->

# test-model

This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.3947
- Accuracy: 0.8833

## Model description

More information needed

## Intended uses & limitations

More information needed

## Training and evaluation data

More information needed

## Training procedure

### Training hyperparameters

The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.3
- num_epochs: 10
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch  | Step | Validation Loss | Accuracy |
|:-------------:|:------:|:----:|:---------------:|:--------:|
| 1.0551        | 0.9960 | 62   | 0.9662          | 0.5412   |
| 0.9308        | 1.9920 | 124  | 0.8707          | 0.5433   |
| 0.7962        | 2.9880 | 186  | 0.7354          | 0.6841   |
| 0.7254        | 4.0    | 249  | 0.7400          | 0.7042   |
| 0.5941        | 4.9960 | 311  | 0.5405          | 0.8169   |
| 0.4736        | 5.9920 | 373  | 0.5045          | 0.8471   |
| 0.4399        | 6.9880 | 435  | 0.4102          | 0.8813   |
| 0.374         | 8.0    | 498  | 0.4052          | 0.8813   |
| 0.3425        | 8.9960 | 560  | 0.4335          | 0.8632   |
| 0.3171        | 9.9598 | 620  | 0.3947          | 0.8833   |


### Framework versions

- Transformers 4.44.0
- Pytorch 2.4.0
- Datasets 2.21.0
- Tokenizers 0.19.1